Device, system, and method of automatically generating an animated content-item

Abstract

Device, system, and method of automatically generating animated content-items. A user operates a smartphone, a tablet, a smart-watch, a computer, or other electronic device, to record an audio segment, and to select a graphical avatar. The audio segment is analyzed by a module that recognizes audio phonemes, and that divides the audio segments into a set of ordered, discrete, audio phonemes. Each audio phoneme is matched with a suitable image that shows the graphical avatar selected by the user, at a particular facial gesture or temporal state that corresponds to utterance of that audio phoneme. An animation sequence is produced, as a data-item or as stand-alone audio/video file. The animated sequence further reflects emotions or mood or other expressions that are identified in the original audio segment. The animation sequence is sent to selected recipients; or is distributed or shared via sharing methods or distribution channels.

What is claimed is: 
     
         1 . A method comprising:
 (a) recording an audio segment uttered by a user of an electronic device;   (b) receiving from said user, a selection of a particular graphical avatar;
 wherein said particular graphical avatar is associated with a set of images, 
 wherein each image of said set of images shows said particular graphical avatar with a different facial gesture; 
   (c) analyzing said audio segment by applying a phonemes recognition technique;   (d) generating a sequence of ordered audio phonemes that correspond to said audio segment;   (e) for each recognized audio phoneme in said sequence, selecting from said set of images, that are associated with said particular graphical avatar, an image which shows said particular graphical avatar performing a facial gesture that matches said recognized audio phoneme;   (f) generating a digital data-item that enables a playback module to playback an animated sequence that matches said audio segment.   
     
     
         2 . The method of  claim 1 , wherein step (g) of generating a digital data-item comprises:
 generating a stand-alone integrated audio/video clip that contains said animated sequence.   
     
     
         3 . The method of  claim 1 , wherein step (g) of generating a digital data-item comprises:
 generating a digital data-item that indicates: (A) which images were selected for said ordered audio phonemes, and (B) an order for displaying the selected images, and (C) a time period for displaying each one of said selected images.   
     
     
         4 . The method of  claim 1 , wherein said electronic device is a device selected from the group consisting of: a smartphone, a tablet, a smart-watch, a wearable electronic device. 
     
     
         5 . The method of  claim 1 , further comprising:
 (h) distributing said stand-alone integrated audio/video clip to one or more recipients selected by said user, via at least one of: a real-time audio/video message exchange platform, a video conference platform, a chat platform, a content-item sharing platform, a content-item distribution platform.   
     
     
         6 . The method of  claim 1 , wherein said electronic device comprises a smartphone;
 wherein step (a) of recording the audio segment comprises: obtaining said audio segment from a voice-message that said user utters via said smartphone through a voice-messaging system.   
     
     
         7 . The method of  claim 1 , wherein said electronic device comprises a smartphone;
 wherein step (a) of recording the audio segment comprises:   (i) intercepting a voice-message that said user utters via said smartphone through a voice-messaging system;   (ii) extracting said audio-segment from said intercepted voice-message that said user uttered;   wherein the method further comprises:   wirelessly transmitting to an intended recipient of said voice-message, said digital data-item that enables a remote smartphone of said intended recipient to playback said animated sequence that matches said audio segment.   
     
     
         8 . The method of  claim 1 , wherein said electronic device comprises a smartphone;
 wherein step (a) of recording the audio segment comprises:   (i) intercepting a voice-message that said user utters via said smartphone through a voice-messaging system;   (ii) extracting said audio-segment from said intercepted voice-message that said user uttered;   wherein the method further comprises:   (A) wirelessly transmitting to an intended recipient of said voice-message, said digital data-item that enables a remote smartphone of said intended recipient to playback said animated sequence that matches said audio segment;   (B) transmitting wirelessly from to said remote smartphone of said intended recipient, a push notification that indicates to the remote smartphone that a new animation sequence coupled to a new audio voice-message are available for playback.   
     
     
         9 . The method of  claim 8 , further comprising:
 (C) receiving from the remote smartphone of the intended recipient, a wireless confirmation signal indicating a download request of said intended recipient;   (D) only after receiving said wireless confirmation signal from said remote smartphone, transmitting wirelessly to the remote smartphone device said digital data-item that enables said remote smartphone to playback the animated sequence that matches said audio segment.   
     
     
         10 . The method of  claim 1 , further comprising:
 storing in a database, that is associated with said electronic device,   (A) multiple representations of graphical avatars that are user-selectable; and   (B) for each graphical avatar, a set of multiple images such that each image shows said graphical avatar with a different facial gesture that corresponds to a different audio phoneme.   
     
     
         11 . The method of  claim 1 , further comprising:
 (A) receiving from said user of said electronic device, a request to select a graphical avatar from a set of multiple user-selectable graphical avatars;   (B) allocating to said user of the first portable electronic device, (i) a selected graphical avatar that said user selected, and (ii) a set of images that show said graphical avatar with different facial gestures that correspond to different audio phonemes.   
     
     
         12 . The method of  claim 1 , further comprising:
 automatically inserting into said animation sequence, an animation effect of a facial gesture based on a pre-defined rule that dictates at least (a) a pre-defined timing scheme for automatic insertion of facial gestures, and (b) which facial gestures to automatically insert.   
     
     
         13 . The method of  claim 1 , further comprising:
 automatically inserting into said animation sequence, an animation effect of a facial gesture based on a pre-defined rule that dictates to automatically insert a particular facial gesture once in every K seconds of animation, wherein K is a positive number.   
     
     
         14 . The method of  claim 1 , further comprising:
 automatically inserting into said animation sequence, an animation effect of a facial gesture based on a pre-defined rule that dictates to automatically insert a particular facial gesture once in every K phonemes, wherein K is a positive number.   
     
     
         15 . The method of  claim 1 , further comprising:
 automatically inserting by said server computer into said animation sequence, an animation effect of a facial gesture based on a pre-defined rule that dictates to automatically insert a particular facial gesture in pseudo-random locations along the animation sequence.   
     
     
         16 . The method of  claim 1 , wherein said audio segment is initially recorded by utilizing a first audio codec;
 wherein the method comprises:   producing said animated sequence which comprises said audio-segment trans-coded by utilizing a second, different, audio codec.   
     
     
         17 . The method of  claim 1 , further comprising:
 receiving from said electronic device, an indication of a genre to which said audio segment belongs;   selecting from a repository of animation effects, a particular animation effect that matches said genre;   inserting said particular animation effect into the animation sequence generated for recognized phonemes of said audio segment.   
     
     
         18 . The method of  claim 1 , further comprising:
 performing contextual analysis of a text message that was composed on said electronic device, to deduce a genre to which said audio segment belongs;   selecting from a repository of animation effects, a particular animation effect that matches said genre of said audio segment;   inserting said particular animation effect into the animation sequence generated for recognized phonemes of said audio segment.   
     
     
         19 . The method of  claim 1 , further comprising:
 performing speech-to-text conversion of said audio segment to automatically generate a transcript of said audio segment;   performing analysis of said transcript of said voice-message, to deduce a genre to which said audio segment belongs;   selecting from a repository of animation effects, a particular animation effect that matches said genre;   inserting said particular animation effect into the animation sequence generated for recognized phonemes of said audio segment.   
     
     
         20 . A device comprising:
 (a) an audio-recording module to record an audio segment uttered by a user of an electronic device;   (b) an avatar-selection module to receive from said user, a selection of a particular graphical avatar;
 wherein said particular graphical avatar is associated with a set of images, 
 wherein each image of said set of images shows said particular graphical avatar with a different facial gesture; 
   (c) an audio analyzer module to analyze said audio segment by applying a phonemes recognition technique;   (d) a sequence generator module to generate a sequence of ordered audio phonemes that correspond to said audio segment;   (e) an image selector module configured to select, for each recognized audio phoneme in said sequence, from said set of images that are associated with said particular graphical avatar, an image which shows said particular graphical avatar performing a facial gesture that matches said recognized audio phoneme;   (f) an animation generator to generate a digital data-item that enables a playback module to playback an animated sequence that matches said audio segment.